##// END OF EJS Templates
bdiff: don't check border condition in loop...
bdiff: don't check border condition in loop `plast = a + len - 1`. So, this "for" loop iterates from "a" to "plast", inclusive. So, `p == plast` can only be true on the final iteration of the loop. So checking for it on every loop iteration is wasteful. This patch simply decreases the upper bound of the loop by 1 and adds an explicit check after iteration for the `p == plast` case. We can't simply add 1 to the initial value for "i" because that doesn't do the correct thing on empty input strings. `perfbdiff -m 3041e4d59df2` on the Firefox repo becomes significantly faster: ! wall 0.072763 comb 0.070000 user 0.070000 sys 0.000000 (best of 100) ! wall 0.053221 comb 0.060000 user 0.060000 sys 0.000000 (best of 100) For the curious, this code has its origins in 8b067bde6679, which is the changeset that introduced bdiff.c in 2005. Also, GNU diffutils is able to perform a similar line-based diff in under 20ms. So there's likely more perf wins to be found in this code. One of them is the hashing algorithm. But it looks like mpm spent some time testing hash collisions in d0c48891dd4a. I'd like to do the same before switching away from lyhash, just to be on the safe side.

File last commit:

r27618:5a988b3c default
r30308:d500ddae default
Show More
lsprofcalltree.py
86 lines | 2.7 KiB | text/x-python | PythonLexer
"""
lsprofcalltree.py - lsprof output which is readable by kcachegrind
Authors:
* David Allouche <david <at> allouche.net>
* Jp Calderone & Itamar Shtull-Trauring
* Johan Dahlin
This software may be used and distributed according to the terms
of the GNU General Public License, incorporated herein by reference.
"""
from __future__ import absolute_import, print_function
def label(code):
if isinstance(code, str):
return '~' + code # built-in functions ('~' sorts at the end)
else:
return '%s %s:%d' % (code.co_name,
code.co_filename,
code.co_firstlineno)
class KCacheGrind(object):
def __init__(self, profiler):
self.data = profiler.getstats()
self.out_file = None
def output(self, out_file):
self.out_file = out_file
print('events: Ticks', file=out_file)
self._print_summary()
for entry in self.data:
self._entry(entry)
def _print_summary(self):
max_cost = 0
for entry in self.data:
totaltime = int(entry.totaltime * 1000)
max_cost = max(max_cost, totaltime)
print('summary: %d' % max_cost, file=self.out_file)
def _entry(self, entry):
out_file = self.out_file
code = entry.code
if isinstance(code, str):
print('fi=~', file=out_file)
else:
print('fi=%s' % code.co_filename, file=out_file)
print('fn=%s' % label(code), file=out_file)
inlinetime = int(entry.inlinetime * 1000)
if isinstance(code, str):
print('0 ', inlinetime, file=out_file)
else:
print('%d %d' % (code.co_firstlineno, inlinetime), file=out_file)
# recursive calls are counted in entry.calls
if entry.calls:
calls = entry.calls
else:
calls = []
if isinstance(code, str):
lineno = 0
else:
lineno = code.co_firstlineno
for subentry in calls:
self._subentry(lineno, subentry)
print(file=out_file)
def _subentry(self, lineno, subentry):
out_file = self.out_file
code = subentry.code
print('cfn=%s' % label(code), file=out_file)
if isinstance(code, str):
print('cfi=~', file=out_file)
print('calls=%d 0' % subentry.callcount, file=out_file)
else:
print('cfi=%s' % code.co_filename, file=out_file)
print('calls=%d %d' % (
subentry.callcount, code.co_firstlineno), file=out_file)
totaltime = int(subentry.totaltime * 1000)
print('%d %d' % (lineno, totaltime), file=out_file)